Facial Sentiment Analysis During Online Classes

Project Title

Facial Sentiment Analysis During Online Classes

Project Area of Specialization Artificial IntelligenceProject Summary

Human activity recognition gained importance in recent years due to its applications in various fields such as security, entertainment and intelligent environment. Activity recognition has received increasing attention from the machine learning community. With the advancements in machine and deep learning algorithms, the envision of various critical real-life applications in computer vision becomes possible. One of the applications is facial sentiment analysis. Deep learning has made facial expression recognition the most trending research fields in computer vision area. With the aid of the use of facial emotion we will get to know about the student potential of learning, concentration and we can determine if the lecture become exciting, boring, or mild for the students. Emotions of a student during course engagement play a vital role in any learning environment whether it's in classrooms or in e-learning. We use excite, disturb and moving pattern of eyes and head to infer meaningful information to understand mood of the student while engaged in an e-learning environment. Evaluating the emotion of a learner can progressively help in enhancing learning experience and update the learning contents. In work from home scenario, it will help us in determining the anxiety or depression of the employees.

Project Objectives

Distance education provides a convenient, fast and economical mode of teaching. However, due to the separation of teachers and students, students cannot exchange timely, dynamic, face-to-face like the conventional education. Some problems of students in the learning process are not solved in time, and their confusion can't get help in the psychological. Students are prone to isolation and loneliness, and thus lose confidence and interest in learning. And it is difficult for students to feel the teachers on their concerns, easily lead to confusion, lazy in the study. so we are trying to develop AI Proctor which will help tutor/teacher to determine the student’s interest and concentration towards topic/lecture. FER technique is used to help in the development of more engaging content. The project purpose is to implement effective e-learning environment as well as Constructive attitude in remote working/jobs from home.

Project Implementation Method

The proposed solution for the Automatic Face Expression Recognition System is composed of a series of modules, with well-defined properties and actions that follow sequential processes. If we look the system from a high grain perspective. its main attributes are identifying the face from a given image, mapping the face pixels into a higher representation and ultimately decide the emotion class. The sequence of steps is:

• Face detection
• Feature Extraction
• preprossesing
• classification

Face detection

Detecting the region of interest represents an essential part of any recognition system Ideally, this process has to be performed automatically and with a very low falsePositive rate. One of the most famous frameworks for object detection that is currentlybeing used is called Viola-Jones.

Feature extraction

Feature extraction is one of the most important stages for any classification system. The choice of algorithms depends not only on the computational properties. But also on the type of data. Asa result, the algorithm that I have chosen to perform feature extraction is Gabor feature extractor which is widely known not only for its computational efficiency, but also for its robustness against illumination changes. To increase its performance, the images are firstly taken though a pre-processing step.

Pre-processing

Raw image data can be corrupted by noise or other unwanted effects, even if the camera or environment remains unchanged. Therefore, before doing any processing toextract meaningful information. the quality of the images has to be improved though a series of operations, known under the term of pre-processing. This solution applies a preProcessing technique called Contrast-limited adaptive histogram equalization, by usingthe Matlab's built-in function, which is used for its property of improving the local contras in the face images.

Classification

The last stage of the system consists of a model that is trained to perform emotionclassification on new images. It uses a Machine Learning classifier called MultilayerNeural Network(MNN), which takes the output of the feature extraction module, thefeature vectors, and learns the patterns that differentiate one emotion from the other.

Benefits of the Project

The advantages of this project are that teacher will able to analyze the behavior and interest of the student’s during lecture or classroom activities. This project will always be beneficial if we look at today’s education system. The online systems not only in education but at every platform consider being beneficial therefore the world is expanding online approach fast. Activity detection through this project will be the path for teachers to observe the interest of their student’s which normally not a simple task in online system. This software will work in the same way for remote workers and identify the attention level of employees.

Technical Details of Final Deliverable

project plan:

• project budget
• project charter

 Requirement specification (document)

• User interface
• Dataset
• Model Training
• Set up of Test system
• Set up of Live system
• Data migration
• User training

Initial briefing report

• Process maps
• Project plan
• Progress reports
• Final report

Final Deliverable of the Project Software SystemCore Industry EducationOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Quality EducationRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	32250
GPU	Equipment	1	30000	30000
Documents printing	Miscellaneous	9	250	2250